Electrode anomaly detection method and device and computer equipment

Abstract

The invention relates to an electrode anomaly detection method and device and computer equipment. The method is applied to the electrical impedance imaging system, the electrical impedance imaging system comprises a plurality of electrodes, and the method comprises the following steps: determining a plurality of groups of excitation electrodes and response electrodes in the plurality of electrodes according to a preset rule; acquiring a plurality of response signals based on each group of excitation electrodes and response electrodes; dividing the plurality of response signals into a plurality of response signal groups according to each group of excitation electrodes and response electrodes; constructing a corresponding first fitting image according to each response signal group; and according to the plurality of first fitting images, determining a target abnormal electrode, thereby realizing rapid positioning of the abnormal electrode.

Description

Technical Field

[0001] The present application relates to the field of EIT imaging technology, and in particular to an electrode abnormality detection method, device, and computer equipment. Background Art

[0002] With the development of medical imaging, EIT (electrical impedance tomography) imaging technology has emerged. Its working principle is to place a certain number of electrodes on the surface of the object to be scanned, inject a safe current and measure the surface voltage of other electrodes, and reconstruct the internal impedance value or the change in impedance value of the object to be scanned based on the relationship between voltage and current for imaging.

[0003] In the related art, although the internal impedance value or the change value of the impedance of the object to be scanned can be reconstructed based on the relationship between voltage and current for imaging, when the displayed image is distorted, the position of the abnormal electrode cannot be quickly located. Summary of the Invention

[0004] Based on this, it is necessary to provide an electrode anomaly detection method, device and computer equipment that can quickly locate abnormal electrodes to address the above technical problems.

[0005] In a first aspect, the present application provides an electrode abnormality detection method, which is applied to an electrical impedance imaging system, wherein the electrical impedance imaging system includes multiple electrodes, and the method includes: determining multiple groups of excitation electrodes and response electrodes among the multiple electrodes according to preset rules; collecting multiple response signals based on each group of excitation electrodes and response electrodes; dividing the multiple response signals into multiple response signal groups based on each group of excitation electrodes and response electrodes; constructing a corresponding first fitting image according to each response signal group; and determining the target abnormal electrode based on the multiple first fitting images.

[0006] In one embodiment, determining multiple groups of excitation electrodes and response electrodes among multiple electrodes according to preset rules includes: taking each electrode as a positive excitation electrode, the opposite electrode as a negative excitation electrode, and the remaining electrodes as response electrodes in turn to determine multiple groups of excitation electrodes and response electrodes; or taking two adjacent electrodes as excitation electrodes and the remaining electrodes as response electrodes in turn to determine multiple groups of excitation electrodes and response electrodes.

[0007] In one embodiment, dividing the plurality of response signals into a plurality of response signal groups based on each group of excitation electrodes and response electrodes includes: dividing the plurality of response signals based on each group of excitation electrodes and response electrodes to determine a plurality of initial response signal groups; using the response signals corresponding to the excitation electrodes in the plurality of initial response signal groups as response signals to be corrected; and setting the response signals to be corrected in the plurality of initial response signal groups to zero to obtain a plurality of response signal groups.

[0008] In one embodiment, constructing a corresponding first fitting image based on each response signal group includes: a plurality of electrodes are respectively assigned consecutive numbers; a plurality of response signals in a target response signal group are sorted in ascending order of numbers, with the response signal collected by an electrode adjacent to the positive stimulation electrode in the direction of increasing numbers as the starting response signal; the target response signal group is any response signal group among the plurality of response signal groups; based on the sorted target response signal group, the amplitude of each response signal is determined; and a first fitting image corresponding to the target response signal group is constructed based on the amplitude of each response signal and the sorted target response signal group.

[0009] In one embodiment, determining the target abnormal electrode based on the multiple first fitting images includes: obtaining a first standard fitting image corresponding to each response signal group; and determining the target abnormal electrode based on the first standard fitting image and the first fitting image corresponding to each response signal group.

[0010] In one embodiment, acquiring the first standard fitting image corresponding to each response signal group includes: acquiring body posture information of the scanned object corresponding to the response signal group; and determining the first standard fitting image corresponding to each response signal group based on the body posture information.

[0011] In one embodiment, determining the target abnormal electrode based on the first standard fitting image and the first fitting image corresponding to each response signal group includes: matching the first standard fitting image of each response signal group with the corresponding first fitting image, and using the electrode of the response signal corresponding to the unmatched position as the initial abnormal electrode of each response signal group; and determining the target abnormal electrode based on the initial abnormal electrode of each response signal group.

[0012] In one embodiment, determining the target abnormal electrode based on the initial abnormal electrode of each response signal group includes: constructing a second fitting image for each response signal based on each response signal in each response signal group; obtaining a second standard fitting image corresponding to each response signal in each response signal group; and determining the target abnormal electrode based on the second standard fitting image and the second fitting image corresponding to each response signal in each response signal group.

[0013] In a second aspect, the present application also provides an electrode abnormality detection device. The device comprises:

[0014] A determination module, configured to determine a plurality of groups of excitation electrodes and response electrodes among a plurality of electrodes according to a preset rule;

[0015] An acquisition module, configured to acquire multiple response signals based on each group of excitation electrodes and response electrodes;

[0016] a dividing module, configured to divide the plurality of response signals into a plurality of response signal groups based on each group of excitation electrodes and response electrodes;

[0017] A construction module, configured to construct a corresponding first fitting image according to each response signal group;

[0018] The determination module is further used to determine the target abnormal electrode based on the multiple first fitting images.

[0019] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements any one of the methods in the first aspect when executing the computer program.

[0020] The above-mentioned electrode abnormality detection method, device and computer equipment determine multiple groups of excitation electrodes and response electrodes among multiple electrodes according to preset rules, and collect multiple response signals based on each group of excitation electrodes and response electrodes; then divide the multiple response signals into multiple response signal groups based on each group of excitation electrodes and response electrodes; and construct a corresponding first fitting image based on each response signal group; finally, determine the target abnormal electrode based on the multiple first fitting images, thereby quickly locating the abnormal electrode. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A diagram showing an application environment of an electrode abnormality detection method in one embodiment;

[0022] Figure 2 1 is a flow chart of a method for detecting an abnormality of an electrode according to an embodiment;

[0023] Figure 3 A schematic diagram of a process divided into multiple response signal groups in one embodiment;

[0024] Figure 4 is a schematic diagram of the layout of multiple electrodes in another embodiment;

[0025] Figure 5 A schematic diagram of a first fitting image of opposed excitation-adjacent measurement in another embodiment;

[0026] Figure 6 A schematic diagram of a first fitting image of adjacent excitation-adjacent measurement in another embodiment;

[0027] Figure 7 is a schematic diagram of a first fitting image of each response signal group during opposing excitation and adjacent measurement in another embodiment;

[0028] Figure 8 A schematic diagram of a first fitting image of each response signal group during adjacent excitation and adjacent measurement in another embodiment;

[0029] Figure 9 Schematic diagram of each second fitting image of the response signal when electrode 1 is used as the positive excitation electrode and electrode 9 is used as the negative excitation electrode in another embodiment;

[0030] Figure 10 Schematic diagram of each second fitting image of the response signal when electrode 1 is used as a positive excitation electrode and electrode 2 is used as a negative excitation electrode in another embodiment;

[0031] Figure 11 is a structural block diagram of an electrode abnormality detection device in one embodiment;

[0032] Figure 12 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0034] EIT technology, the full name of which is bioelectrical impedance tomography, is a new type of medical functional imaging technology. Its working principle is to place a certain number of electrodes on the surface of the object to be scanned, inject a safe current and measure the surface voltage of other electrodes, and reconstruct the internal impedance value of the object to be scanned or the change value of the impedance according to the relationship between voltage and current for imaging. Since this method does not use radionuclides or rays for imaging, it is harmless to the object to be scanned, so it can be measured and reused many times, and the imaging speed is fast, with the characteristics of functional imaging. EIT technology has many advantages, such as being non-invasive to the scanned object, no ionization and radiation hazards, simple system structure, easy measurement, etc. It can be used in fast portable imaging applications, and has broad application prospects in continuous dynamic image monitoring of physiological activities of the cardiovascular, esophageal, gastric, etc. of the object to be scanned.

[0035] Since the EIT (electrical impedance tomography) system needs to traverse all electrode positions for stimulation, the 16 electrodes will form 256 independent measurement channels (16×16), and these response signals constitute the basic data source for the system to reconstruct images. However, related technologies have obvious limitations in evaluating signal quality: most systems rely only on a single numerical threshold judgment (such as a signal-to-noise ratio greater than 55dB) or visual inspection of the reconstructed image to identify abnormal signals, and lack intuitive analytical tools for the spatial distribution characteristics of the original signal. In related technologies, although the internal electrical impedance value or the change in electrical impedance of the object to be scanned can be reconstructed based on the relationship between voltage and current for imaging, when the displayed image is distorted, the position of the abnormal electrode cannot be quickly located.

[0036] The electrode abnormality detection method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 via a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 is used to execute the electrode anomaly detection method. The server 104 can be implemented as an independent server or a server cluster consisting of multiple servers.

[0037] In order to solve the above problem, in one embodiment of the present application, Figure 2 As shown, a method for detecting an electrode abnormality is provided, which is applied to an electrical impedance tomography system, wherein the electrical impedance tomography system includes a plurality of electrodes, and the method includes the following steps:

[0038] Step 201: Determine multiple groups of excitation electrodes and response electrodes from multiple electrodes according to a preset rule.

[0039] That is, multiple electrodes in the electrical impedance tomography system are grouped based on preset rules to obtain multiple groups of excitation electrodes and corresponding response electrodes, wherein there are duplicate electrodes between each group of excitation electrodes and response electrodes.

[0040] The preset rules include adjacent excitation-adjacent measurement or opposite excitation-adjacent measurement. Adjacent excitation-adjacent measurement involves using two adjacent electrodes among a plurality of electrodes as excitation electrodes and measuring the responses of the two adjacent electrodes. Opposite excitation-adjacent measurement involves using two opposite electrodes among a plurality of electrodes as excitation electrodes and measuring the responses of the two adjacent electrodes.

[0041] Among them, the excitation electrode is an electrode that generates excitation to the electrical impedance imaging system and outputs the excitation to the object to be scanned, and the response electrode is an electrode that collects the response of the object to be scanned based on the excitation after the excitation electrode outputs the excitation to the object to be scanned.

[0042] It should be noted that the objects to be scanned are materials with different electrical conductivities, such as the human body, fluids (oil / water / gas), solid particles and fluids, rocks / soils with different porosities, healthy and damaged materials, and areas with different moisture contents.

[0043] Step 202: Collect multiple response signals based on each group of excitation electrodes and response electrodes.

[0044] The response signal is the response of the scanned object to the stimulus output by the electrical impedance imaging system, measured on each response electrode. In this embodiment, the response signal is a voltage differential signal, i.e., the difference between the signals of two response electrodes. After receiving the voltage signals of the two response electrodes, the two signals are subtracted to obtain the response signal. The response electrodes are all electrodes in the plurality of electrodes except the stimulus electrode.

[0045] That is, under the action of the excitation electrodes of each group, the response signals are collected on the response electrodes of each group.

[0046] Step 203 : Divide the multiple response signals into multiple response signal groups based on each group of excitation electrodes and response electrodes.

[0047] That is, the multiple response signals collected are grouped according to each group of excitation electrodes and response electrodes to obtain multiple response signal groups, wherein each response signal group corresponds to each group of excitation electrodes and response electrodes.

[0048] Step 204: construct a corresponding first fitting image according to each response signal group.

[0049] The first fitting image is a fitting image constructed based on the response signal group, and in this embodiment, is a saddle diagram.

[0050] That is, a first fitting image corresponding to each response signal group is constructed according to each response signal group.

[0051] Specifically, after the amplitude values ​​of the response signals are acquired, a first fitting image is constructed according to the order of the response electrodes.

[0052] Step 205: Determine target abnormal electrodes based on the multiple first fitting images.

[0053] For example, under ideal circumstances, the fitting curve of the first fitting image is a continuous saddle diagram. When there is an anomaly, the fitting curve of the first fitting image will be distorted. The abnormal response signal can be located according to the position where the distortion occurs, and the response electrode corresponding to the abnormal response signal can be used as the target abnormal electrode.

[0054] The target abnormal electrode is an electrode with an abnormality in the electrical impedance imaging system. For example, if an electrode has a poor contact problem with the object to be scanned, the electrode is the target abnormal electrode.

[0055] In the above-mentioned electrode abnormality detection method, multiple groups of excitation electrodes and response electrodes are determined among multiple electrodes according to preset rules, and multiple response signals are collected based on each group of excitation electrodes and response electrodes; then the multiple response signals are divided into multiple response signal groups based on each group of excitation electrodes and response electrodes; and a corresponding first fitting image is constructed based on each response signal group; finally, based on the multiple first fitting images, the target abnormal electrode is determined, thereby quickly locating the abnormal electrode.

[0056] For example, Figure 4 As shown, multiple electrodes in the electrical impedance tomography system adopt a ring layout.

[0057] In other embodiments of the present application, determining multiple groups of excitation electrodes and response electrodes from multiple electrodes according to a preset rule includes:

[0058] Each electrode is sequentially used as a positive excitation electrode, the opposite electrode is used as a negative excitation electrode, and the remaining electrodes are used as response electrodes, thereby determining multiple groups of excitation electrodes and response electrodes.

[0059] It should be noted that the preset rules include two measurement modes: opposite excitation-adjacent measurement and adjacent excitation-adjacent measurement.

[0060] For example, in a specific embodiment of the present application, the multiple electrodes are 16 electrodes distributed in a ring, and the opposite excitation-adjacent measurement is: electrode 1 is used as the positive excitation electrode, electrode 9 is used as the negative excitation electrode, and all electrodes except electrode 1 and electrode 9 are used as response electrodes, thereby determining a group of excitation electrodes and response electrodes in the multiple groups of excitation electrodes and response electrodes.

[0061] For example, in a specific embodiment of the present application, the multiple electrodes are 16 electrodes distributed in a ring, and the opposite excitation-adjacent measurement is: electrode 2 is used as the positive excitation electrode, electrode 10 is used as the negative excitation electrode, and all electrodes except electrode 2 and electrode 10 are used as response electrodes, thereby determining a group of excitation electrodes and response electrodes in the multiple groups of excitation electrodes and response electrodes.

[0062] For example, in a specific embodiment of the present application, the multiple electrodes are 16 electrodes distributed in a ring, and the opposite excitation-adjacent measurement is: electrode 3 is used as the positive excitation electrode, electrode 11 is used as the negative excitation electrode, and all electrodes except electrode 3 and electrode 11 are used as response electrodes, thereby determining a group of excitation electrodes and response electrodes in the multiple groups of excitation electrodes and response electrodes.

[0063] Alternatively, two adjacent electrodes are sequentially used as excitation electrodes and the remaining electrodes are used as response electrodes to determine multiple groups of excitation electrodes and response electrodes.

[0064] For example, in a specific embodiment of the present application, the multiple electrodes are 16 electrodes distributed in a ring, and the adjacent excitation-adjacent measurement is to use electrode 1 as the positive excitation electrode, electrode 2 as the negative excitation electrode, and all electrodes except electrode 1 and electrode 2 as response electrodes, thereby determining a group of excitation electrodes and response electrodes in the multiple groups of excitation electrodes and response electrodes.

[0065] For example, in a specific embodiment of the present application, the multiple electrodes are 16 electrodes distributed in a ring, and the adjacent excitation-adjacent measurement is to use electrode 2 as the positive excitation electrode, electrode 3 as the negative excitation electrode, and all electrodes except electrode 2 and electrode 3 as response electrodes, thereby determining a group of excitation electrodes and response electrodes in the multiple groups of excitation electrodes and response electrodes.

[0066] For example, in a specific embodiment of the present application, the multiple electrodes are 16 electrodes distributed in a ring, and the adjacent excitation-adjacent measurement is to use electrode 3 as the positive excitation electrode, electrode 4 as the negative excitation electrode, and all electrodes except electrode 3 and electrode 4 as response electrodes, thereby determining a group of excitation electrodes and response electrodes in the multiple groups of excitation electrodes and response electrodes.

[0067] In other embodiments of the present application, Figure 3 As shown, dividing the plurality of response signals into a plurality of response signal groups based on each group of excitation electrodes and response electrodes includes:

[0068] Step 301: Divide a plurality of response signals into groups of excitation electrodes and response electrodes to determine a plurality of initial response signal groups.

[0069] That is, the multiple response signals collected are grouped according to each group of excitation electrodes and response electrodes to obtain multiple initial response signal groups, wherein each initial response signal group corresponds to each group of excitation electrodes and response electrodes.

[0070] Exemplarily, when electrode 1 is used as a positive excitation electrode and electrode 9 is used as a negative excitation electrode, all electrodes except electrode 1 and electrode 9 are used as response electrodes, and the multiple response signals obtained constitute a set of initial response signal groups.

[0071] Exemplarily, when electrode 2 is used as a positive excitation electrode and electrode 10 is used as a negative excitation electrode, all electrodes except electrode 2 and electrode 10 are used as response electrodes, and the multiple response signals obtained constitute a set of initial response signal groups.

[0072] Step 302: Use the response signals corresponding to the excitation electrodes in the multiple initial response signal groups as the response signals to be corrected.

[0073] It should be noted that the response signal is the voltage differential signal between the two response electrodes, that is, the signal difference between the two response electrodes. Specifically, after receiving the voltage signals of the two response electrodes, the two signals are subtracted to obtain the response signal. The response signal to be corrected is the response signal of the corresponding two response electrodes, including the response signal of the excitation electrode.

[0074] For example, when electrode 1 is used as a positive excitation electrode and electrode 9 is used as a negative excitation electrode, the signal collected between electrode 1 and electrode 2, the signal collected between electrode 8 and electrode 9, the signal collected between electrode 9 and electrode 10, and the signal collected between electrode 16 and electrode 1 are all response signals to be corrected.

[0075] Step 303: Set the response signals to be corrected in the multiple initial response signal groups to zero to obtain multiple response signal groups.

[0076] That is, the value of the response signal to be corrected in each initial response signal group is set to zero, thereby obtaining multiple response signal groups.

[0077] It should be noted that in actual application scenarios, the response signals to be corrected are regarded as invalid data. If the first fitting image is constructed together with each response signal to be corrected and other valid response signals, the fitting curve of the first fitting image will be abnormal, making it impossible to determine the target abnormal electrode. Setting each response signal to be corrected to zero can effectively prevent the occurrence of the above situation.

[0078] In other embodiments of the present application, constructing a corresponding first fitting image according to each response signal group includes:

[0079] Step 1: sort the multiple response signals in the target response signal group in ascending order of numbers, starting with the response signal collected by the electrode adjacent to the positive stimulation electrode in the direction of increasing numbers as the starting response signal.

[0080] Table 1

[0081]

[0082] For example, for opposite excitation-adjacent measurement, as shown in Table 1, with electrode 1 as the positive excitation electrode and electrode 9 as the negative excitation electrode, the response signals are as follows: collecting the response signals of electrodes 2 and 3; collecting the response signals of electrodes 3 and 4; collecting the response signals of electrodes 4 and 5; collecting the response signals of electrodes 5 and 6; collecting the response signals of electrodes 6 and 7; collecting the response signals of electrodes 7 and 8; collecting the response signals of electrodes 10 and 11; collecting the response signals of electrodes 11 and 12; collecting the response signals of electrodes 12 and 13; collecting the response signals of electrodes 13 and 14; collecting the response signals of electrodes 14 and 15; collecting the response signals of electrodes 15 and 16. Among them, the response signals of electrodes 2 and 3 are the initial response signals.

[0083] Table 2

[0084]

[0085] For example, as shown in Table 2 above, for adjacent excitation-adjacent measurement, with electrode 1 as the positive excitation electrode and electrode 2 as the negative excitation electrode, the response signals are as follows: collecting the response signals of electrodes 3 and 4; collecting the response signals of electrodes 4 and 5; collecting the response signals of electrodes 5 and 6; collecting the response signals of electrodes 6 and 7; collecting the response signals of electrodes 7 and 8; collecting the response signals of electrodes 8 and 9; collecting the response signals of electrodes 9 and 10; collecting the response signals of electrodes 10 and 11; collecting the response signals of electrodes 11 and 12; collecting the response signals of electrodes 12 and 13; collecting the response signals of electrodes 13 and 14; collecting the response signals of electrodes 14 and 15; collecting the response signals of electrodes 15 and 16. Among them, the response signals of electrodes 3 and 4 are the initial response signals.

[0086] The multiple electrodes are respectively corresponding to consecutive numbers; the target response signal group is any response signal group among the multiple response signal groups.

[0087] It should be noted that although the target response signal group is one of the multiple response signal groups, in actual situations, the relevant steps in this embodiment will be performed separately on each of the multiple response signal groups.

[0088] It is worth noting that the Figure 5 The first fitting image of the opposite excitation-adjacent measurement is shown. Figure 6 The first fitting image of adjacent excitation-adjacent measurement is shown. Figure 7 FIG1 shows the first fitting image of each response signal group during the opposite excitation-adjacent measurement. For example, 1-9 represent the positive excitation electrode of the first fitting image as electrode 1 and the negative excitation electrode as electrode 9. Figure 8It shows the first fitting image of each response signal group during adjacent excitation-adjacent measurement. For example, 1-2 represents the positive excitation electrode of the first fitting image as electrode 1 and the negative excitation electrode as electrode 2.

[0089] Step 2: Based on the sorted target response signal group, determine the amplitude of each response signal.

[0090] It should be noted that the response signal is a voltage differential signal between two response electrodes, and the amplitude of the response signal is the voltage amplitude of the voltage differential signal between the two response electrodes.

[0091] Step 3: Construct a first fitting image corresponding to the target response signal group according to the amplitude of each response signal and the sorted target response signal group.

[0092] That is, based on the order of each response signal in the sorted target response signal group and according to the amplitude of each response signal in the target response signal group, fitting is performed to obtain a first fitting image corresponding to the target response signal group.

[0093] In other embodiments of the present application, determining target abnormal electrodes according to the plurality of first fitting images includes:

[0094] Step 1: Obtain the first standard fitting image corresponding to each response signal group.

[0095] The first standard fitting image is a standard fitting image that matches the body shape of the scanned subject and has no abnormalities in the multiple electrodes. It should be noted that the fitting curve of the fitting image is also related to the chest size and chest shape of the scanned subject.

[0096] It should be noted that in an ideal uniform medium, the fitting curve of the fitting image should present a symmetrical saddle shape. However, in the case of simulating the chest shape, the fitting curve of the fitting image will have a slight deformation, and the fitting curve of the fitting image is also related to the chest size and chest shape of the scanned object. According to the chest size and chest shape of the scanned object, a suitable first standard fitting image can be selected for comparison with the first fitting image.

[0097] Step 2: Determine the target abnormal electrode according to the first standard fitting image and the first fitting image corresponding to each response signal group.

[0098] That is, the target abnormal electrode is determined by comparing the similarities and differences between the fitting curve of the first standard fitting image and the fitting curve of the first fitting image corresponding to each response signal group.

[0099] In other embodiments of the present application, obtaining the first standard fitting image corresponding to each response signal group includes:

[0100] Step 1: Obtain the body posture information of the scanned object corresponding to the response signal group.

[0101] The scanned object is the object to be subjected to electrical impedance tomography, and the body shape information is the body shape-related information of the scanned object, such as the chest size and chest shape of the scanned object.

[0102] Step 2: Determine the first standard fitting image corresponding to each response signal group based on the body posture information.

[0103] That is, according to the body posture information of the scanned object, a first standard fitting image corresponding to the body posture information of the scanned object is determined.

[0104] It should be noted that in a certain embodiment of the present application, a database of various different body posture information and corresponding first standard fitting images is pre-constructed, and a query can be performed based on the body posture information of the actual scanned object to obtain the first standard fitting image corresponding to the body posture information of the actual scanned object.

[0105] In other embodiments of the present application, determining the target abnormal electrode according to the first standard fitting image and the first fitting image corresponding to each response signal group includes:

[0106] Step 1: Match the first standard fitting image of each response signal group with the corresponding first fitting image respectively, and use the electrodes of the response signals corresponding to the unmatched positions as the initial abnormal electrodes of each response signal group.

[0107] That is, the first standard fitting image of each response signal group is compared with the corresponding first fitting image respectively, so as to determine the response electrodes of the response signals corresponding to multiple mismatching positions, and the determined electrodes are used as the initial abnormal electrodes of each response signal group.

[0108] For example, in actual application scenarios, there are generally two situations for the fitting curve of the abnormal first fitting image. One of them is: the excitation electrode corresponding to the first fitting image is abnormal. In this case, the overall fitting curve of the first fitting image is severely distorted and does not correspond to the fitting curve of the first standard fitting image at all. The excitation electrode corresponding to the fitting image is used as the initial abnormal electrode. The other situation is: the response electrode corresponding to the first fitting image is abnormal. In this case, the fitting curve of the first fitting image is partially distorted. When compared with the fitting curve of the first standard fitting image, some curves do not correspond. The response signal closest to the non-corresponding curve is found, and the two response electrodes corresponding to the response signal are used as the initial abnormal electrodes.

[0109] It should be noted that analyzing only one first fitting image can only identify two initial abnormal electrodes, but cannot determine which of these two initial abnormal electrodes is the target abnormal electrode where the abnormality actually occurred. Therefore, it is necessary to analyze each first fitting image to determine the initial abnormal electrode for each response signal group, laying the foundation for later determining the target abnormal electrode where the abnormality actually occurred.

[0110] Step 2: Determine the target abnormal electrode based on the initial abnormal electrode of each response signal group.

[0111] That is, repeated initial abnormal electrodes are determined from the initial abnormal electrodes of each response signal group, and the repeated initial abnormal electrodes are used as target abnormal electrodes.

[0112] For example, if electrode 1 is abnormal, electrode 1 must exist in the initial abnormal electrodes of each response signal group. Based on the initial abnormal electrodes of each response signal group, the step of determining the target abnormal electrode is actually the process of taking the intersection of the initial abnormal electrodes of each response signal group, and the intersection is the target abnormal electrode.

[0113] In other embodiments of the present application, determining the target abnormal electrode according to the initial abnormal electrode of each response signal group includes:

[0114] Step 1: Construct a second fitting image of each response signal according to each response signal in each response signal group.

[0115] In this embodiment, the second fitting image is a sinusoidal waveform diagram of the response signal.

[0116] For example, the Figure 9 As shown in FIG. 1 , the second fitting images of the response signals when electrode 1 is a positive excitation electrode and electrode 9 is a negative excitation electrode are shown in FIG. Figure 10 As shown, there are respective second fitting images of the response signal when electrode 1 is used as the positive excitation electrode and electrode 2 is used as the negative excitation electrode.

[0117] Step 2: Obtain a second standard fitting image corresponding to each response signal in each response signal group.

[0118] The second standard fitting image is a standard sine waveform diagram of the response signal.

[0119] Step 3: Determine the target abnormal electrode according to the second standard fitting image and the second fitting image corresponding to each response signal in each response signal group.

[0120] That is, by comparing the second standard fitting image and the second fitting image corresponding to each response signal in each response signal group, the abnormal response signal in each response signal group is determined, and then the target abnormal electrode is determined based on the correspondence between the response signal and the response electrode.

[0121] For example, when there is an abnormality in electrode 1, after comparing the second standard fitting image and the second fitting image corresponding to each response signal in each response signal group, the intersection of the initial abnormal electrodes corresponding to the abnormal response signals in each response signal group must include electrode 1, and the target abnormal electrode can be determined by taking the intersection of the initial abnormal electrodes corresponding to each response signal group.

[0122] In a specific embodiment of the present application, the electrode abnormality detection method includes:

[0123] Stimulus Grouping and Reorganization: 256 original response signals are regrouped according to the location of the stimulation electrodes, forming 16 independent signal groups (one group corresponds to each stimulation location). Each group contains 12 valid measurement signals (12 valid data points for opposing stimulations and 13 valid data points for adjacent stimulations) (since the stimulation electrodes themselves do not participate in the measurement). The system automatically inserts a zero value or marker bit to complete the 16-channel response signal group. This reorganization method breaks away from traditional time-series arrangement and constructs a data set centered on the stimulation source.

[0124] Each signal group is sorted by starting with the positively stimulated electrode, creating a visual signal saddle plot. The X-axis of the saddle plot represents the electrode number starting with the positive stimulation, and the Y-axis represents the normalized signal amplitude. In an ideal homogeneous medium, the curve should exhibit a symmetrical saddle shape. When simulating the shape of the chest cavity, a slightly deformed saddle shape can also be achieved. The electrode closest to the stimulation point has the highest signal amplitude (peak), while the diagonal region has the lowest amplitude (trough).

[0125] Spatial topological mapping: The reorganized response signal groups are spatially arranged according to the actual physical locations of the electrodes on the body surface. When the electrode array adopts a circular layout (such as for chest cross-sectional monitoring), the 16 electrodes form a 16×16 two-dimensional matrix. Each element in the matrix represents the signal amplitude of a specific stimulation-measurement electrode pair (i, j), where the row index corresponds to the stimulation electrode location and the column index corresponds to the measurement electrode location. This mapping directly links the abstract electrical signal to the physical spatial location.

[0126] Electrode loss detection: Based on the combination of 16 excitation electrodes, the electrode loss can be determined based on the completeness of the response signal. The problematic electrodes can also be found based on the waveform size pattern of the saddle diagram, and the spacing or electrode position can be adjusted.

[0127] Adaptive saddle diagram baseline: In an ideal homogeneous medium, the fitting curve should present a symmetrical saddle shape. When simulating the chest shape, a slightly deformed saddle shape can also be presented. Enter the chest size and basic chest shape, select the appropriate standard fitting image for comparison, and the operator can adjust the electrode according to the saddle diagram.

[0128] It should be noted that at the beginning of response signal acquisition, the first and second fitting images can be directly viewed. Based on the display results of these two types of images, according to basic rules (in an ideal homogeneous medium, the curve should present a symmetrical saddle shape. In a simulated chest cavity shape, it can also present a slightly deformed saddle shape: the electrode closest to the excitation point obtains the highest signal amplitude (peak), and the diagonal area forms the lowest amplitude (trough), abnormal electrodes can be identified and adjusted directly until the electrode adjustment is completed and data acquisition is carried out. Storing the original signal, time, and event also facilitates postoperative data playback analysis. In addition, if all the response signals of the corresponding excitation electrodes are distorted, at least one of the corresponding two excitation electrodes is off. If there is partial distortion in the response signal of the corresponding excitation electrode, at least one of the corresponding receiving electrodes is off.

[0129] It should be noted that the above-mentioned electrode anomaly detection method has the following advantages in terms of clinical visualization: it can provide the operator with an intuitive signal-electrode mapping diagram, so that the electrode contact status can be directly judged based on the signal integrity; and it can facilitate the rapid judgment of the electrode contact status and electrode spacing in clinical monitoring scenarios (the 16 electrodes must be evenly distributed on the surface of the object to be scanned); in addition, it can also determine the first standard fitting image based on the chest shape and chest size of different scanned objects, so that the operator can adjust the electrodes more accurately.

[0130] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0131] Based on the same inventive concept, embodiments of the present application also provide an electrode anomaly detection device for implementing the aforementioned electrode anomaly detection method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations in one or more embodiments of the electrode anomaly detection device provided below can be found in the limitations of the electrode anomaly detection method described above and will not be further elaborated here.

[0132] In one embodiment of the present application, Figure 11 As shown, an electrode abnormality detection device is provided, comprising:

[0133] The determination module 100 is configured to determine a plurality of groups of excitation electrodes and response electrodes from a plurality of electrodes according to a preset rule.

[0134] The acquisition module 200 is configured to acquire a plurality of response signals based on each group of excitation electrodes and response electrodes.

[0135] The division module 300 is configured to divide the plurality of response signals into a plurality of response signal groups based on each group of excitation electrodes and response electrodes.

[0136] The construction module 400 is configured to construct a corresponding first fitting image according to each response signal group.

[0137] The determination module 100 is further configured to determine target abnormal electrodes based on the plurality of first fitting images.

[0138] The determination module 100 is also used to sequentially use each electrode as a positive excitation electrode, the opposite electrode as a negative excitation electrode, and the remaining electrodes as response electrodes to determine multiple groups of excitation electrodes and response electrodes; or sequentially use two adjacent electrodes as excitation electrodes and the remaining electrodes as response electrodes to determine multiple groups of excitation electrodes and response electrodes.

[0139] The division module 300 is further configured to divide the plurality of response signals into each group of excitation electrodes and response electrodes to determine a plurality of initial response signal groups; use the response signals corresponding to the excitation electrodes in the plurality of initial response signal groups as response signals to be corrected; and set the response signals to be corrected in the plurality of initial response signal groups to zero to obtain a plurality of response signal groups.

[0140] Construction module 400 is further configured to sort multiple response signals in a target response signal group in ascending order of numbers, starting with a response signal collected by an electrode adjacent to the positive stimulation electrode in an increasing number direction as a starting response signal; the target response signal group being any response signal group among the multiple response signal groups; determining an amplitude of each response signal based on the sorted target response signal group; and constructing a first fitting image corresponding to the target response signal group based on the amplitude of each response signal and the sorted target response signal group.

[0141] The determination module 100 is further configured to obtain a first standard fitting image corresponding to each response signal group; and determine a target abnormal electrode based on the first standard fitting image corresponding to each response signal group and the first fitting image.

[0142] The determination module 100 is further configured to obtain body posture information of the scanned object corresponding to the response signal group; and determine a first standard fitting image corresponding to each response signal group based on the body posture information.

[0143] The determination module 100 is also used to match the first standard fitting image of each response signal group with the corresponding first fitting image, and use the electrode of the response signal corresponding to the unmatched position as the initial abnormal electrode of each response signal group; and determine the target abnormal electrode based on the initial abnormal electrode of each response signal group.

[0144] The determination module 100 is further used to construct a second fitting image for each response signal according to each response signal in each response signal group; obtain a second standard fitting image corresponding to each response signal in each response signal group; and determine the target abnormal electrode according to the second standard fitting image and the second fitting image corresponding to each response signal in each response signal group.

[0145] Each module in the aforementioned electrode anomaly detection device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0146] In one embodiment of the present application, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 12As shown. The computer device includes a processor, a memory and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store all relevant data for executing the electrode abnormality detection method. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, an electrode abnormality detection method is implemented.

[0147] Those skilled in the art will understand that Figure 12 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0148] In one embodiment of the present application, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the electrode abnormality detection method in the above embodiment are implemented.

[0149] In one embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. The computer program is executed by a processor to implement the steps of the electrode abnormality detection method in the above-mentioned method embodiments.

[0150] In one embodiment of the present application, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps of the electrode abnormality detection method in the above-mentioned method embodiments.

[0151] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0152] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The above-mentioned computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. Among them, any reference to memory, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, and the like.

[0153] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0154] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for detecting an electrode abnormality, characterized in that: Applied to an electrical impedance tomography system, the electrical impedance tomography system comprising a plurality of electrodes, the method comprising: Determining multiple groups of excitation electrodes and response electrodes among the multiple electrodes according to preset rules; Based on each group of excitation electrodes and response electrodes, multiple response signals are collected; Dividing the plurality of response signals into a plurality of response signal groups based on each group of excitation electrodes and response electrodes; Constructing a corresponding first fitting image according to each response signal group; A target abnormal electrode is determined based on the plurality of first fitting images.

2. The electrode abnormality detection method according to claim 1, characterized in that: The determining of multiple groups of excitation electrodes and response electrodes from multiple electrodes according to a preset rule includes: sequentially using each electrode as a positive excitation electrode, the opposite electrode as a negative excitation electrode, and the remaining electrodes as response electrodes to determine multiple groups of excitation electrodes and response electrodes; or Two adjacent electrodes are sequentially used as excitation electrodes and the remaining electrodes are used as response electrodes to determine multiple groups of excitation electrodes and response electrodes.

3. The electrode abnormality detection method according to claim 1, characterized in that: The step of dividing the plurality of response signals into a plurality of response signal groups based on each group of excitation electrodes and response electrodes comprises: Dividing the plurality of response signals into each group of excitation electrodes and response electrodes to determine a plurality of initial response signal groups; taking the response signals corresponding to the excitation electrodes in the plurality of initial response signal groups as response signals to be corrected; The response signals to be corrected in the plurality of initial response signal groups are set to zero to obtain a plurality of response signal groups.

4. The electrode abnormality detection method according to claim 1, characterized in that: The step of constructing a corresponding first fitting image according to each response signal group includes: the plurality of electrodes are respectively numbered consecutively; Sorting the multiple response signals in the target response signal group in ascending order of numbers, starting with the response signal collected by the electrode adjacent to the positive stimulation electrode in the direction of increasing numbers as the starting response signal; the target response signal group is any response signal group in the multiple response signal groups; determining the amplitude of each response signal based on the sorted target response signal group; A first fitting image corresponding to the target response signal group is constructed according to the amplitude of each response signal and the sorted target response signal group.

5. The electrode abnormality detection method according to claim 1, characterized in that: The determining of target abnormal electrodes according to the plurality of first fitting images comprises: Obtaining a first standard fitting image corresponding to each response signal group; The target abnormal electrode is determined according to the first standard fitting image and the first fitting image corresponding to each response signal group.

6. The electrode abnormality detection method according to claim 5, characterized in that: The obtaining of the first standard fitting image corresponding to each response signal group includes: Acquiring body posture information of a scanned object corresponding to the response signal group; A first standard fitting image corresponding to each response signal group is determined according to the body posture information.

7. The electrode abnormality detection method according to claim 5, characterized in that: Determining the target abnormal electrode according to the first standard fitting image and the first fitting image corresponding to each response signal group includes: Matching the first standard fitting image of each response signal group with the corresponding first fitting image respectively, and taking the electrodes of the response signals corresponding to the mismatched positions as the initial abnormal electrodes of each response signal group; According to the initial abnormal electrodes of each response signal group, the target abnormal electrodes are determined.

8. The electrode abnormality detection method according to claim 7, characterized in that: Determining the target abnormal electrode according to the initial abnormal electrode of each response signal group includes: constructing a second fitting image for each response signal according to each response signal in each response signal group; Acquire a second standard fitting image corresponding to each response signal in each response signal group; The target abnormal electrode is determined according to the second standard fitting image and the second fitting image corresponding to each response signal in each response signal group.

9. An electrode abnormality detection device, characterized in that: The device comprises: A determination module, configured to determine a plurality of groups of excitation electrodes and response electrodes among a plurality of electrodes according to a preset rule; An acquisition module, configured to acquire multiple response signals based on each group of excitation electrodes and response electrodes; a dividing module, configured to divide the plurality of response signals into a plurality of response signal groups based on each group of excitation electrodes and response electrodes; A construction module, configured to construct a corresponding first fitting image according to each response signal group; The determination module is further used to determine the target abnormal electrode based on the multiple first fitting images.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images